Results 1 to 10 of about 2,818,371 (325)
DINOv2: Learning Robust Visual Features without Supervision [PDF]
Trans. Mach. Learn. Res., 2023 The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
M. Oquab +25 more
semanticscholar +1 more source
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision [PDF]
Computer Vision and Pattern Recognition, 2021 In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS).
Xiaokang Chen +3 more
semanticscholar +1 more source
GroupViT: Semantic Segmentation Emerges from Text Supervision [PDF]
Computer Vision and Pattern Recognition, 2022 Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens implicitly via top-down supervision ...
Jiarui Xu +6 more
semanticscholar +1 more source
Discovering Latent Knowledge in Language Models Without Supervision [PDF]
International Conference on Learning Representations, 2022 Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors ...
Collin Burns +3 more
semanticscholar +1 more source
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision [PDF]
Computer Vision and Pattern Recognition, 2022 We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and bet-suits modern image backbones. Existing state-of-the-art BEV detectors are often tied to certain depth pretrained backbones like Vo Vn et ...
Chenyu Yang +11 more
semanticscholar +1 more source
CLAP Learning Audio Concepts from Natural Language Supervision
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 Mainstream machine listening models are trained to learn audio concepts under the paradigm of one class label to many recordings focusing on one task.
Benjamin Elizalde +3 more
semanticscholar +1 more source
EnlightenGAN: Deep Light Enhancement Without Paired Supervision [PDF]
IEEE Transactions on Image Processing, 2019 Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data?
Yifan Jiang +8 more
semanticscholar +1 more source
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation [PDF]
Computer Vision and Pattern Recognition, 2021 Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects.
Seungho Lee +3 more
semanticscholar +1 more source
SSRN Electronic Journal, 2022 We exploit the establishment of a supranational supervisor in Europe (the Single Supervisory Mechanism) to learn how the organizational design of supervisory institutions impacts the enforcement of financial regulation. Banks under supranational supervision are required to increase regulatory capital for exposures to the same firm compared to banks ...
Haselmann, Rainer +2 more
openaire +4 more sources
Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports [PDF]
Nature Machine Intelligence, 2021 Pre-training lays the foundation for recent successes in radiograph analysis supported by deep learning. It learns transferable image representations by conducting large-scale fully- or self-supervised learning on a source domain; however, supervised pre-
H.-Y. Zhou +5 more
semanticscholar +1 more source