United States

Self-supervised learning (SSL) techniques have recently been integrated into the few-shot learning (FSL) framework and have shown promising results in improving the few-shot image classification performance. However, existing SSL approaches used in FSL typically seek the supervision signals from the global embedding of every single image. Therefore, during the episodic training of FSL, these methods cannot capture and fully utilize the local visual information in image samples and the data structure information of the whole episode, which are beneficial to FSL. To this end, we propose to augment the few-shot learning objective with a novel self-supervised Episodic Spatial Pretext Task (ESPT). Specifically, for each few-shot episode, we generate its corresponding transformed episode by applying a random geometric transformation to all the images in it. Based on these, our ESPT objective is defined as maximizing the local spatial relationship consistency between the original episode and the transformed one. With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples. Extensive experiments indicate that our ESPT method achieves new state-of-the-art performance for few-shot image classification on three mainstay benchmark datasets. The source code will be available at: https://github.com/Whut-YiRong/ESPT (Pytorch) and https://gitee.com/Yi-Rong/ESPT (MindSpore).

AAAI 2023

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

ml: unsupervised & self-supervised learning

ml: classification and regression

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

poster

A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations.
We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. 

We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced  annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies.
Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but  struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models.

VASR: Visual Analogies of Situation Recognition

Recommender systems now consume large-scale data and play a significant role in improving user experience. Graph Neural Networks (GNNs) have emerged as one of the most effective recommender system models because they model the rich relational information. The ever-growing volume of data can make training GNNs prohibitively expensive. To address this, previous attempts propose to train the GNN models incrementally as new data blocks arrive. 
Feature and structure knowledge distillation techniques have been explored to allow the GNN model to train in a fast incremental fashion while alleviating the catastrophic forgetting problem. 
However, fully preserving the historical information for all users is sub-optimal since it fails to take into account the dynamics of each user's change of preferences. 
For the users whose interests shift substantially, retaining too much of the old knowledge can overly constrain the model, preventing it from quickly adapting to the users’ novel interests. 
In contrast, for users who have static preferences, model performance can benefit greatly from preserving as much of the user's long-term preferences as possible.
In this work, we propose a novel training strategy that adaptively learns personalized imitation weights for each user to balance the contribution from the recent data and the amount of knowledge to be distilled from previous time periods.
We demonstrate the effectiveness of learning imitation weights via a comparison on five diverse datasets for three state-of-art structure distillation-based recommender systems. The performance shows consistent improvement over competitive incremental learning techniques. We make our code available \url{https://anonymous.4open.science/r/SAIL-PIW-22BD}.

Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems

Fine-Grained Image Classification (FGIC) aims to classify images into specific subordinate classes of a superclass. Due to insufficient training data and confusing data samples, FGIC may produce uncertain classification results that are untrusted for data applications. In fact, FGIC can be viewed as a hierarchical classification process and the multilayer information facilitates to reduce  uncertainty and improve the reliability of FGIC. In this paper, we adopt the evidence theory to measure uncertainty and confidence in hierarchical classification process and propose a trusted FGIC method through fusing multilayer classification evidence. Comparing with the traditional approaches, the trusted FGIC method not only generates accurate classification results but also reduces the uncertainty of fine-grained classification. Specifically, we construct an evidence extractor at each classification layer to extract multilayer (multi-grained) evidence for image classification. To fuse the extracted multi-grained evidence from coarse to fine, we formulate  evidence fusion with the Dirichlet hyper probability distribution and thereby hierarchically decompose the evidence of coarse-grained classes into fine-grained classes to enhance the classification performances. The ablation experiments validate that the hierarchical evidence fusion can improve the precision and also reduce the uncertainty of fine-grained classification. The comparison with state-of-the-art FGIC methods shows that our proposed method achieves competitive performances.

Trusted Fine-grained Image Classification Through Hierarchical Evidence Fusion

Visual Question Answering (VQA) aims to answer the natural language question about a given image by understanding multimodal content. However, the answer quality of most existing visual-language pre-training (VLP) methods is still limited, mainly due to: \textbf{(1) \emph{Incompatibility.}} Upstream pre-training tasks are generally incompatible with downstream question answering tasks, which makes the knowledge from the language model not well transferable to downstream tasks, and greatly limits their performance in few-shot scenarios; \textbf{(2) \emph{Under-fitting.}} they generally do not integrate human priors to compensate for universal knowledge from language models, so as to fit the challenging VQA problem and generate reliable answers. To address these issues, we propose HybridPrompt, a \emph{cloze-} and \emph{verify-style} hybrid prompt framework with bridging language models and human priors in prompt tuning for VQA.
Specifically, we first modify the input questions into the \emph{cloze-style} prompts to narrow the gap between upstream pre-training tasks and downstream VQA task, which ensures that the universal knowledge in the language model can be better transferred to subsequent human prior-guided prompt tuning. Then, we imitate the cognitive process of human brain to introduce topic and sample related priors to construct a dynamic learnable prompt template for human prior-guided prompt learning. Finally, we add fixed-length learnable free-parameters to further enhance the generalizability and scalability of prompt learning in the VQA model.
Experimental results verify the effectiveness of HybridPrompt, showing that it achieves competitive performance against previous methods on widely-used VQAv2 dataset and obtains new state-of-the-art results. Our code is released at: \url{https://github.com/AnonymousPony/hybrid}.

HybridPrompt: Bridging Language Models and Human Priors in Prompt Tuning for Visual Question Answering

In the submodular ranking (SR) problem, the input consists of a set of submodular functions defined on a ground set of elements. The goal is to order elements for all the functions to have value above a certain threshold as soon on average as possible, assuming we choose one element per time. The problem is flexible enough to capture various applications in machine learning, including decision trees. 

This paper considers the min-max version of SR where multiple instances share the ground set. With the view of each instance being associated with an agent, the min-max problem is to order the common elements to minimize the maximum objective of all agents---thus, finding a fair solution for all agents. We give approximation algorithms for this problem and demonstrate their effectiveness in the application of finding a decision tree for multiple agents. 

Min-Max Submodular Ranking for Multiple Agents

Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form of a (partial) model of this environment to decide upon the safety of an action. A so-called shield forces the RL agent to select only safe actions. However, for adoption in various applications, one must look beyond enforcing safety and also ensure the applicability of RL with good performance. We extend the applicability of shields via tight integration with state-of-the-art deep RL, and provide an extensive, empirical study in challenging, sparse-reward environments under partial observability. We show that a carefully integrated shield ensures safety and can improve the convergence rate and final performance of RL agents. We furthermore show that a shield can be used to bootstrap state-of-the-art RL agents: they remain safe after initial learning in a shielded setting, allowing us to disable a potentially too conservative shield eventually.

Safe Reinforcement Learning via Shielding under Partial Observability

Steganography is a technique that hides secret messages into a public multimedia object without raising suspicion from third parties. However, most existing works cannot provide good robustness against lossy JPEG compression while maintaining a relatively large embedding capacity. This paper presents an end-to-end robust steganography system based on the invertible neural network (INN). Instead of hiding in the spatial domain, our method directly hides secret messages into the discrete cosine transform (DCT) coefficients of the cover image, which significantly improves the robustness and anti-steganalysis security. A mutual information loss is first proposed to constrain the flow of information in INN. Besides, a two-way fusion module (TWFM) is implemented, utilizing spatial and DCT domain features as auxiliary information to facilitate message extraction. These two designs aid in recovering secret messages from the DCT coefficients losslessly. Experimental results demonstrate that our method yields significantly lower error rates than other existing hiding methods. For example, our method achieves reliable extraction with 0 error rate for 1 bit per pixel (bpp) embedding payload; and under the JPEG compression with quality factor QF=10, the error rate of our method is about 22% lower than the state-of-the-art robust image hiding methods, which demonstrates remarkable robustness against JPEG compression.

Robust Image Steganography: Hiding Messages in Frequency Coefficients

Neural networks have complex structures, and thus it is hard to understand their inner workings and ensure correctness. To understand and debug convolutional neural networks (CNNs) we propose techniques for testing the channels of CNNs. We design FtGAN, an extension to GAN, that can generate test data with varying the intensity (i.e., sum of the neurons) of a channel of a target CNN. We also proposed a channel selection algorithm to find representative channels for testing. To efficiently inspect the target CNN’s inference computations, we define unexpectedness score, which estimates how similar the inference computation of the test data is to that of the training data. We evaluated FtGAN with five public datasets and showed that our techniques successfully identify defective channels in five different CNN models.

Testing the Channels of Convolutional Neural Networks

Deep neural networks are in the limelight of machine learning with their excellent performance in many data-driven applications. However, they can lead to inaccurate predictions when queried in out-of-distribution data points, which can have detrimental effects especially in sensitive domains, such as healthcare and transportation, where erroneous predictions can be very costly and/or dangerous. Subsequently, quantifying the uncertainty of the output of a neural network is often leveraged to evaluate the confidence of its predictions, and ensemble models have proved to be effective in measuring the uncertainty by utilizing the variance of predictions over a pool of models. In this paper, we propose a novel approach for uncertainty quantification via ensembles, called Random Activation Functions (RAFs) Ensemble, that aims at improving the ensemble diversity toward a more robust estimation, by accommodating each neural network with a different (random) activation function. Extensive empirical study demonstrates that RAFs Ensemble outperforms state-of-the-art ensemble uncertainty quantification methods on both synthetic and real-world datasets in a series of regression tasks.

Toward Robust Uncertainty Estimation with Random Activation Functions

Estimating the causal effects of a spatially-varying intervention on a spatially-varying outcome may be subject to non-local confounding (NLC), a phenomenon that can bias estimates when the treatments and outcomes of a given unit are dictated in part by the covariates of other nearby units. In particular, NLC is a challenge for evaluating the effects of environmental policies and climate events on health-related outcomes such as air pollution exposure. This paper first formalizes NLC using the potential outcomes framework, providing a comparison with the related phenomenon of causal interference. Then, it proposes a broadly applicable framework, termed weather2vec, that uses the theory of balancing scores to learn representations of non-local information into a scalar or vector defined for each observational unit, which is subsequently used to adjust for confounding in conjunction with causal inference methods. The framework is evaluated in a simulation study and two case studies on air pollution where the weather is an (inherently regional) known confounder.

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

Downloads

Next from AAAI 2023

VASR: Visual Analogies of Situation Recognition

Similar lecture

Centerless Multi-View K-means Based on The Adjacency Matrix

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES