Related papers: Counterfactual Co-occurring Learning for Bias Miti…

Weakly Supervised Object Detection (WSOD), using only image-level annotations to train object detectors, is of growing importance in object recognition. In this paper, we propose a novel deep network for WSOD. Unlike previous networks that…

The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning which needs high-quality manual labeled data. The experiments under the UCL paradigm indicate a phenomenon…

In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand,…

Visual Language Navigation (VLN) is a fundamental task within the field of Embodied AI, focusing on the ability of agents to navigate complex environments based on natural language instructions. Despite the progress made by existing…

Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on a variety of subsequent tasks (in particular…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Object-context shortcuts remain a persistent challenge in vision-language models, undermining zero-shot reliability when test-time scenes differ from familiar training co-occurrences. We recast this issue as a causal inference problem and…

Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity of tasks arising in existing benchmarks, recent methods use…

Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL). However, CAM directly uses the classifier trained…

Typically, objects with the same semantics are not always prominent in images containing different backgrounds. Motivated by this observation that accurately salient object detection is related to both foreground and background, we proposed…

Recent advances in open-vocabulary object detection focus primarily on two aspects: scaling up datasets and leveraging contrastive learning to align language and vision modalities. However, these approaches often neglect internal…

In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video transformer which are used in parallel to generate diverse…

Malicious image manipulation poses societal risks, increasing the importance of effective image manipulation detection methods. Recent approaches in image manipulation detection have largely been driven by fully supervised approaches, which…

Weakly-supervised Temporal Action Localization (WTAL) aims to detect the action segments with only video-level action labels in training. The key challenge is how to distinguish the action of interest segments from the background, which is…

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…

Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances. For this, the model must identify features indicative of…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…