paper-with-me

홈 › Papers

ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation

2021-03-01 · Vinay Kaushik, Kartik Jindgar, Brejesh lall

Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learning accurate and robust depth. We propose a relational self-attention module that learns rich contextual features and further enhances depth results. We also optimize the auto-masking strategy across all losses by enforcing L1 regularisation over mask. Our novel progressive training strategy first learns depth at a lower resolution and then progresses to the original resolution with slight training. We utilise a ResNet18 encoder, learning features for prediction of both depth and pose. We evaluate our predicted depth on the standard KITTI driving dataset and achieve state-of-the-art results for monocular depth estimation whilst having significantly lower number of trainable parameters in our deep learning framework. We also evaluate our model on Make3D dataset showing better generalization than other methods.

📄 PDF Abstract BibTeX arXiv:2103.00853

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDepth EstimationMonocular Depth EstimationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

2022-06-16 · Viraj Prabhu, Sriram Yenamandra, Aaditya Singh, Judy Hoffman

Visual domain adaptation (DA) seeks to transfer trained models to unseen, unlabeled domains across distribution shift, but approaches typically focus on adapting convolutional neural network architectures initialized wit…

Domain AdaptationObject RecognitionSelf-Supervised Learning

Unsupervised Adaptation of Question Answering Systems via Generative Self-training

2020-11-01 · EMNLP 2020 11 · Steven Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo 외

BERT-era question answering systems have recently achieved impressive performance on several question-answering (QA) tasks. These systems are based on representations that have been pre-trained on self-supervised tasks s…

Question AnsweringSentence

Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

2023-03-02 · Rundong Luo, Yifei Wang, Yisen Wang

Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (s…

Contrastive LearningData AugmentationSelf-Supervised Learning

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

2026-07-02 · Dengyang Jiang, Mengmeng Wang, Harry Yang, Jingdong Wang arxiv

Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on…

Data Augmentation

Self-Adapting Language Models

2025-06-12 · Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek 외

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to…

Data Augmentation