Listwise Reward Estimation for Offline Preference-based Reinforcement Learning

In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from human feedback. However, existing PbRL methods have limitations as they often overlook the second-order preference that indicates the relative strength of preference. In this paper, we propose Listwise Reward Estimation (LiRE), a novel approach for offline PbRL that leverages second-order preference information by constructing a Ranked List of Trajectories (RLT), which can be efficiently built by using the same ternary feedback type as traditional methods. To validate the effectiveness of LiRE, we propose a new offline PbRL dataset that objectively reflects the effect of the estimated rewards. Our extensive experiments on the dataset demonstrate the superiority of LiRE, i.e., outperforming state-of-the-art baselines even with modest feedback budgets and enjoying robustness with respect to the number of feedbacks and feedback noise. Our code is available at https://github.com/chwoong/LiRE

Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable searches. Due to the expensive dataset construction cost for CIR triplets, a zero-shot (ZS) CIR setting has been actively studied to eliminate the need for human-collected triplet datasets. The mainstream of ZS-CIR employs an efficient projection module that projects a CLIP image embedding to the CLIP text token embedding space, while fixing the CLIP encoders. Using the projected image embedding, these methods generate image-text composed features by using the pre-trained text encoder. However, their CLIP image and text encoders suffer from the task discrepancy between the pre-training task (text $\leftrightarrow$ image) and the target CIR task (image + text $\leftrightarrow$ image). Conceptually, we need expensive triplet samples to reduce the discrepancy, but we use cheap text triplets instead and update the text encoder. To that end, we introduce the Reducing Task Discrepancy of text encoders for Composed Image Retrieval (RTD), a plug-and-play training scheme for the text encoder that enhances its capability using a novel target-anchored text contrastive learning. We also propose two additional techniques to improve the proposed learning scheme: a hard negatives-based refined batch sampling strategy and a sophisticated concatenation scheme. Integrating RTD into the state-of-the-art projection-based ZS-CIR methods significantly improves performance across various datasets and backbones, demonstrating its efficiency and generalizability.

Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation

This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with different pixel labels, which is far from practical incremental learning scenarios. Moreover, we identified that this flawed scenario may lead to biased results for two commonly used techniques in CISS, pseudo-labeling and exemplar memory, resulting in unintended advantages or disadvantages for certain techniques. To mitigate this, a practical scenario called partitioned is proposed, in which the dataset is first divided into distinct subsets representing each class, and then the subsets are assigned to each corresponding task. This efficiently addresses the issue above while meeting the requirement of CISS scenario, such as capturing the background shifts. Furthermore, we identify and address the code implementation issues related to retrieving data from the exemplar memory, which was ignored in previous works. Lastly, we introduce a simple yet competitive memory-based baseline, MiB-AugM, that handles background shifts of current tasks in the exemplar memory. This baseline achieves state-of-the-art results across multiple tasks involving learning numerous new classes.

Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning

We argue that one of the main obstacles for developing effective Continual Reinforcement Learning (CRL) algorithms is the negative transfer issue occurring when the new task to learn arrives. Through comprehensive experimental validation, we demonstrate that such issue frequently exists in CRL and cannot be effectively addressed by several recent work on mitigating plasticity loss of RL agents. To that end, we develop Reset & Distill (R&D), a simple yet highly effective method, to overcome the negative transfer problem in CRL. R&D combines a strategy of resetting the agent's online actor and critic networks to learn a new task and an offline learning step for distilling the knowledge from the online actor and previous expert's action probabilities. We carried out extensive experiments on long sequence of Meta-World tasks and show that our method consistently outperforms recent baselines, achieving significantly higher success rates across a range of tasks. Our findings highlight the importance of considering negative transfer in CRL and emphasize the need for robust strategies like R&D to mitigate its detrimental effects.

Converting and Smoothing False Negatives for Vision-Language Pre-training

We consider the critical issue of false negatives in Vision-Language Pre-training (VLP), a challenge that arises from the inherent many-to-many correspondence of image-text pairs in large-scale web-crawled datasets. The presence of false negatives can impede achieving optimal performance and even lead to learning failures. To address this challenge, we propose a method called COSMO (COnverting and SMOoothing false negatives) that manages the false negative issues, especially powerful in hard negative sampling. Building upon the recently developed GRouped mIni-baTch sampling (GRIT) strategy, our approach consists of two pivotal components: 1) an efficient connection mining process that identifies and converts false negatives into positives, and 2) label smoothing for the image-text contrastive loss (ITC). Our comprehensive experiments verify the effectiveness of COSMO across multiple downstream tasks, emphasizing the crucial role of addressing false negatives in VLP, potentially even surpassing the importance of addressing false positives. In addition, the compatibility of COSMO with the recent BLIP-family model is also demonstrated.

TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers

A classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last Layer Retraining (LLR) with group-balanced datasets is known to be efficient in mitigating the spurious correlation of classifiers. However, the acquisition of group-balanced datasets is costly, which hinders the applicability of the LLR method. In this work, we propose to perform LLR based on text datasets built with large language models for a general image classifier. We demonstrate that text can be a proxy for its corresponding image beyond the image-text joint embedding space, such as CLIP. Based on this, we use generated texts to train the final layer in the embedding space of the arbitrary image classifier. In addition, we propose a method of filtering the generated words to get rid of noisy, imprecise words, which reduces the effort of inspecting each word. We dub these procedures as TLDR (\textbf{T}ext-based \textbf{L}ast layer retraining for \textbf{D}ebiasing image classifie\textbf{R}s) and show our method achieves the performance that is comparable to those of the LLR methods that also utilize group-balanced image dataset for retraining. Furthermore, TLDR outperforms other baselines that involve training the last linear layer without a group annotated dataset.

SwiFT: Swin 4D fMRI Transformer

The modeling of spatiotemporal brain dynamics from high-dimensional data, such as 4D functional MRI, is a formidable task in neuroscience. To address this challenge, we present SwiFT (Swin 4D fMRI Transformer), a Swin Transformer architecture that can learn brain dynamics directly from 4D functional brain MRI data in a memory and computation-efficient manner. SwiFT achieves this by implementing a 4D window multi-head self-attention mechanism and absolute positional embeddings. We evaluate SwiFT using multiple largest-scale human functional brain imaging datasets in tasks such as predicting sex, age, and cognitive intelligence. Our experimental outcomes reveal that SwiFT consistently outperforms recent state-of-the-art models. To the best of our knowledge, SwiFT is the first Swin Transformer architecture that can process dimensional spatiotemporal brain functional data in an end-to-end fashion. Furthermore, due to the end-to-end learning capability, we also show that contrastive loss-based self-supervised pre-training of SwiFT is also feasible for achieving improved performance on a downstream task. We believe that our work holds substantial potential in facilitating scalable learning of functional brain imaging in neuroscience research by reducing the hurdles associated with applying Transformer models to high-dimensional fMRI.

Sy-CON: Symmetric Contrastive Loss for Continual Self-Supervised Representation Learning

We introduce a novel and general loss function, called Symmetric Contrastive (Sy-CON) loss, for effective continual self-supervised learning (CSSL). We first argue that the conventional loss form of continual learning which consists of single task-specific loss (for plasticity) and a regularizer (for stability) may not be ideal for contrastive loss based CSSL that focus on representation learning. Our reasoning is that, in contrastive learning based methods, the task-specific loss would suffer from decreasing diversity of negative samples and the regularizer may hinder learning new distinctive representations. To that end, we propose Sy-CON that consists of two losses (one for plasticity and the other for stability) with symmetric dependence on current and past models' negative sample embeddings. We argue our model can naturally find good trade-off between the plasticity and stability without any explicit hyperparameter tuning. We validate the effectiveness of our approach through extensive experiments, demonstrating that MoCo-based implementation of Sy-CON loss achieves superior performance compared to other state-of-the-art CSSL methods.

Continual Learning in the Presence of Spurious Correlation

Most continual learning (CL) algorithms have focused on tackling the stability-plasticity dilemma, that is, the challenge of preventing the forgetting of previous tasks while learning new ones. However, they have overlooked the impact of the knowledge transfer when the dataset in a certain task is biased - namely, when some unintended spurious correlations of the tasks are learned from the biased dataset. In that case, how would they affect learning future tasks or the knowledge already learned from the past tasks? In this work, we carefully design systematic experiments using one synthetic and two real-world datasets to answer the question from our empirical findings. Specifically, we first show through two-task CL experiments that standard CL methods, which are unaware of dataset bias, can transfer biases from one task to another, both forward and backward, and this transfer is exacerbated depending on whether the CL methods focus on the stability or the plasticity. We then present that the bias transfer also exists and even accumulate in longer sequences of tasks. Finally, we propose a simple, yet strong plug-in method for debiasing-aware continual learning, dubbed as Group-class Balanced Greedy Sampling (BGS). As a result, we show that our BGS can always reduce the bias of a CL model, with a slight loss of CL performance at most.

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Many existing group fairness-aware training methods aim to achieve the group fairness by either re-weighting underrepresented groups based on certain rules or using weakly approximated surrogates for the fairness metrics in the objective as regularization terms. Although each of the learning schemes has its own strength in terms of applicability or performance, respectively, it is difficult for any method in the either category to be considered as a gold standard since their successful performances are typically limited to specific cases. To that end, we propose a principled method, dubbed as \ours, which unifies the two learning schemes by incorporating a well-justified group fairness metric into the training objective using a class wise distributionally robust optimization (DRO) framework. We then develop an iterative optimization algorithm that minimizes the resulting objective by automatically producing the correct re-weights for each group. Our experiments show that FairDRO is scalable and easily adaptable to diverse applications, and consistently achieves the state-of-the-art performance on several benchmark datasets in terms of the accuracy-fairness trade-off, compared to recent strong baselines.