Related papers: Selective Contrastive Learning for Weakly Supervis…
Understanding objects in terms of their individual parts is important, because it enables a precise understanding of the objects' geometrical structure, and enhances object recognition when the object is seen in a novel pose or under…
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…
The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…
Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…
Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and…
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…
Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing…
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small and sparse…
Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this problem is quite challenging due to the lack of location…
Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…
Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on…
Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks…
Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary annotation. The crux of this task lies in locating each…
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…
Affordance detection refers to identifying the potential action possibilities of objects in an image, which is an important ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we consider…
In this work, we focus on Weakly Supervised Spatio-Temporal Video Grounding (WSTVG). It is a multimodal task aimed at localizing specific subjects spatio-temporally based on textual queries without bounding box supervision. Motivated by…
Few-Shot learning aims to train and optimize a model that can adapt to unseen visual classes with only a few labeled examples. The existing few-shot learning (FSL) methods, heavily rely only on visual data, thus fail to capture the semantic…
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(WSOD), have recently…
We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing…