Canada

Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap between different modalities, most existing trackers are designed for single or partial of these reference settings and overspecialize on the specific modality. Differently, we present a unified tracker called UVLTrack, which can simultaneously handle all three reference settings (BBOX, NL, NL+BBOX) with the same parameters. The proposed UVLTrack enjoys several merits. First, we design a modality-unified feature extractor for joint visual and language feature learning and propose a multi-modal contrastive loss to align the visual and language features into a unified semantic space. Second, a modality-adaptive box head is proposed, which makes full use of the target reference to mine ever-changing scenario features dynamically from video contexts and distinguish the target in a contrastive way, enabling robust performance in different reference settings. Extensive experimental results demonstrate that UVLTrack achieves promising performance on seven visual tracking datasets, three vision-language tracking datasets, and three visual grounding datasets. Codes and models are open-sourced at https://github.com/OpenSpaceAI/UVLTrack.

AAAI 2024

Unifying Visual and Vision-Language Tracking via Contrastive Learning

cv: motion & tracking

cv: multi-modal vision

cv: language and vision

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects, resulting in fragmented motion estimation. Through theoretical analysis, we find the pre-trained large vision models are helpful in optical flow estimation, and we notice that the recently famous Segment Anything Model (SAM) demonstrates a strong ability to segment complete objects, which is suitable for solving the fragmentation problem. We thus propose a solution to embed the frozen SAM image encoder into FlowFormer to enhance object perception. To address the challenge of in-depth utilizing SAM in non-segmentation tasks like optical flow estimation, we propose an Optical Flow Task-Specific Adaption scheme, including a Context Fusion Module to fuse the SAM encoder with the optical flow context encoder, and a Context Adaption Module to adapt the SAM features for optical flow task with Learned Task-Specific Embedding. Our proposed SAMFlow model reaches 0.86/2.10 clean/final EPE and 3.55/12.32 EPE/F1-all on Sintel and KITTI-15 training set, surpassing Flowformer by 8.5%/9.9% and 13.2%/16.3%. Furthermore, our model achieves state-of-the-art performance on the Sintel and KITTI-15 benchmarks, ranking #1 among all two-frame methods on Sintel clean pass.

SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model

In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet. Code and models are publicly available.

Understanding the Role of the Projector in Knowledge Distillation

We propose novel fast algorithms for optimal transport (OT) utilizing a cyclic symmetry structure of input data. Such OT with cyclic symmetry appears universally in various real-world examples: image processing, urban planning, and graph processing. Our main idea is to reduce OT to a small optimization problem that has significantly fewer variables by utilizing cyclic symmetry and various optimization techniques. On the basis of this reduction, our algorithms solve the small optimization problem instead of the original OT. As a result, our algorithms obtain the optimal solution and the objective function value of the original OT faster than solving the original OT directly. In this paper, our focus is on two crucial OT formulations: the linear programming OT (LOT) and the strongly convex-regularized OT, which includes the well-known entropy-regularized OT (EROT). Experiments show the effectiveness of our algorithms for LOT and EROT in synthetic/real-world data that has a strict/approximate cyclic symmetry structure. Through theoretical and experimental results, this paper successfully introduces the concept of symmetry into the OT research field for the first time.

Optimal Transport with Cyclic Symmetry

Causal inference from longitudinal observational data is a challenging problem due to the difficulty in correctly identifying the time-dependent confounders, especially in the presence of latent time-dependent confounders. Instrumental variable (IV) is a powerful tool for addressing the latent confounders issue, but the traditional IV technique cannot deal with latent time-dependent confounders in longitudinal studies. In this work, we propose a novel Time-dependent Instrumental Factor Model (TIFM) for time-varying causal effect estimation from data with latent time-dependent confounders. At each time-step, the proposed TIFM method employs the Recurrent Neural Network (RNN) architecture to infer latent IV, and then uses the inferred latent IV factor for addressing the confounding bias caused by the latent time-dependent confounders. We provide a theoretical analysis for the proposed TIFM method regarding causal effect estimation in longitudinal data. Extensive evaluation with synthetic datasets demonstrates the effectiveness of TIFM in addressing causal effect estimation over time. We further apply TIFM to a climate dataset to showcase the potential of the proposed method in tackling real-world problems.

Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounders

Single-exposure high dynamic range (HDR) imaging aims
to reconstruct the wide-range intensities of a scene by using
its single low dynamic range (LDR) image, thus providing
significant efficiency. Existing methods pay high attention to
restoring the luminance by inversing the tone-mapping process,
while the color in the over-/under-exposed area cannot
be well restored due to the information loss of the single
LDR image. To address this issue, we introduce color
events into the imaging pipeline, which record asynchronous
pixel-wise color changes in a high dynamic range, enabling
edge-like scene perception under challenging lighting conditions.
Specifically, we propose a joint framework that incorporates
color events and a single LDR image to restore
both content and color of an HDR image, where an exposureaware
transformer (EaT) module is designed to propagate the
informative hints, provided by the normal-exposed LDR regions
and the event streams, to the missing areas. In this
module, an exposure-aware mask is estimated to suppress
distractive information and strengthen the restoration of the
over-/under-exposed regions. To our knowledge, we are the
first to use color events to enhance single-exposure HDR
imaging. We also contribute corresponding datasets, consisting
of synthesized datasets and a real-world dataset collected
by a DAVIS346-color camera. The datasets can be found at
https://www.kaggle.com/datasets/mengyaocui/ce-hdr. Extensive
experiments demonstrate the effectiveness of the proposed
method.

Color Event Enhanced Single-Exposure HDR Imaging

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. 
However, the conventional MoE architecture with parallel Feed Forward Network (FFN) experts leads to significant parameter and computational overheads that hinder its efficient deployment. In addition, the naive  MoE linear router is suboptimal in assigning task-specific features to multiple experts which limits its further scalability.  
In this work, we propose an efficient MoE architecture with weight sharing across the experts. Inspired by the idea of linear feature modulation (FM), our architecture implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. 
The proposed Feature Modulated Expert (FME) serves as a building block for the novel Mixture-of-Feature-Modulation-Experts (MoFME) architecture, which can scale up the number of experts with low overhead.
We further propose an Uncertainty-aware Router (UaR) to assign task-specific features to different FM modules with well-calibrated weights. This enables MoFME to effectively learn diverse expert functions for multiple tasks. 
The conducted experiments on the multi-deweather task show that our MoFME outperforms the state-of-the-art in the image restoration quality by 0.1-0.2 dB while saving more than 74% of parameters and 20% inference time over the conventional MoE counterpart. Experiments on the downstream segmentation and classification tasks further demonstrate the generalizability of MoFME to real open-world applications.

Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation

Recently, arbitrary text style transfer (TST) has made significant progress with the paradigm of prompt learning. In this paradigm, researchers often design or search for a fixed prompt for any input. However, existing evidence shows that large language models (LLMs) are prompt-sensitive and it is sub-optimal to apply the same prompt to any input for downstream TST tasks. Besides, the prompts obtained by searching are often unreadable and unexplainable to humans. To address these issues, we propose an Adaptive Prompt Routing (APR) framework to adaptively route prompts from a human-readable prompt set for various input texts and given styles. Specifically, we first construct a candidate prompt set of diverse and human-readable prompts for the target style. This set consists of several seed prompts and their variants paraphrased by an LLM. Subsequently, we train a prompt routing model to select the optimal prompts efficiently according to inputs. The adaptively selected prompt can guide the LLMs to perform a precise style transfer for each input sentence while maintaining readability for humans. Extensive experiments on 4 public TST benchmarks over 3 popular LLMs (with parameter sizes ranging from 1.5B to 175B) demonstrate that our APR achieves superior style transfer performances, compared to the state-of-the-art prompt-based and fine-tuning methods.

Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models

With the increasing customization of spectrometers, spectral unmixing has become a widely used technique in fields such as remote sensing, textiles, and environmental protection.
However, endmember variability is a common issue for unmixing, where changes in lighting, atmospheric, temporal conditions, or the intrinsic spectral characteristics of materials, can all result in variations in the measured spectrum.
Recent studies have employed deep neural networks to tackle endmember variability. However, these approaches rely on generic networks to implicitly resolve the issue, which struggles with the ill-posed nature and lack of effective convergence constraints for endmember variability. This paper proposes a streamlined multi-task learning model to rectify this problem, incorporating abundance regression and multi-label classification with Unmixing as a Bayesian Inverse Problem, denoted as BIPU. 
To address the issue of the ill-posed nature, the uncertainty of unmixing is quantified and minimized through the Laplace approximation in a Bayesian inverse solver. In addition, to improve convergence under the influence of endmember variability, the paper introduces two types of constraints. The first separates background factors of variants from the initial factors for each endmember, while the second identifies and eliminates the influence of non-existent endmembers via multi-label classification during convergence.
The effectiveness of this model is demonstrated not only on a self-collected near-infrared spectral textile dataset (FENIR), but also on three commonly used remote sensing hyperspectral image datasets, where it achieves state-of-the-art unmixing performance and exhibits strong generalization capabilities.

Solving Spectrum Unmixing as a Multi-Task Bayesian Inverse Problem with Latent Factors for Endmember Variability

Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by {\bf 16\%} of the RMSE of the whole image on the LRSS dataset.
Our data and code is available at: \url{https://github.com/jinyeying/DeS3_Deshadow}.

DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity

Recently, self-supervised monocular depth estimation has gained popularity with numerous applications in autonomous driving and robotics. However, existing solutions primarily seek to estimate depth from immediate visual features, and struggle to recover fine-grained scene details. In this paper, we introduce SQLdepth, a novel approach that can effectively learn fine-grained scene structure priors from ego-motion. In SQLdepth, we propose a novel Self Query Layer (SQL) to build a self-cost volume and infer depth from it, rather than inferring depth from feature maps. We show that, the self-cost volume is an effective inductive bias for geometry learning, which implicitly models the single-frame scene geometry, with each slice of it indicating a relative distance map between points and objects in a latent space. Experimental results on KITTI and Cityscapes show that our method attains remarkable state-of-the-art performance, and showcases computational efficiency, reduced training complexity, and the ability to recover fine-grained scene details. Moreover, the self-matching-oriented relative distance querying in SQL improves the robustness and zero-shot generalization capability of SQLdepth. Code is available at \textcolor{purple!75}{https://github.com/hisfog/SfMNeXt-Impl}.

Content not yet available

Unifying Visual and Vision-Language Tracking via Contrastive Learning

Downloads

Next from AAAI 2024

SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

Unifying Visual and Vision-Language Tracking via Contrastive Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads