Related papers: Improving Weakly-supervised Object Localization vi…
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from…
Image colourisation is an ill-posed problem, with multiple correct solutions which depend on the context and object instances present in the input datum. Previous approaches attacked the problem either by requiring intense user interactions…
We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals.…
In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations…
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel…
For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extracting discriminative local features play a crucial role in…
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…
In this paper we address the problem of unsupervised localization of objects in single images. Compared to previous state-of-the-art method our method is fully unsupervised in the sense that there is no prior instance level or category…
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from…
Existing Camouflaged Object Detection (COD) methods rely heavily on large-scale pixel-annotated training sets, which are both time-consuming and labor-intensive. Although weakly supervised methods offer higher annotation efficiency, their…
Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…
Class activation map (CAM) has been widely used to highlight image regions that contribute to class predictions. Despite its simplicity and computational efficiency, CAM often struggles to identify discriminative regions that distinguish…
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in…
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models. Such models are traditionally learned from images/videos labelled only with the object class and not the object bounding box.…
This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then…
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only…
VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images. However, existing approaches rely heavily on fully supervised learning with expensive cross-modality…
Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of…