Cosine meets Softmax: A tough-to-beat baseline for visual grounding

09/13/2020
by   Nivedita Rufus, et al.
3

In this paper, we present a simple baseline for visual grounding for autonomous driving which outperforms the state of the art methods, while retaining minimal design choices. Our framework minimizes the cross-entropy loss over the cosine distance between multiple image ROI features with a text embedding (representing the give sentence/phrase). We use pre-trained networks for obtaining the initial embeddings and learn a transformation layer on top of the text embedding. We perform experiments on the Talk2Car dataset and achieve 68.7 investigation suggests reconsideration towards more approaches employing sophisticated attention mechanisms or multi-stage reasoning or complex metric learning loss functions by showing promise in simpler alternatives.

READ FULL TEXT

page 2

page 4

page 8

page 9

research
09/11/2018

Heated-Up Softmax Embedding

Metric learning aims at learning a distance which is consistent with the...
research
03/30/2022

SeqTR: A Simple yet Universal Network for Visual Grounding

In this paper, we propose a simple yet universal network termed SeqTR fo...
research
11/22/2017

Conditional Image-Text Embedding Networks

This paper presents an approach for grounding phrases in images which jo...
research
11/28/2018

Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding

We address the problem of phrase grounding by learning a multi-level com...
research
03/31/2020

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification

Despite the growing popularity of metric learning approaches, very littl...
research
09/20/2023

Sentence Attention Blocks for Answer Grounding

Answer grounding is the task of locating relevant visual evidence for th...
research
11/12/2021

Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

Few-shot object detection (FSOD) localizes and classifies objects in an ...

Please sign up or login with your details

Forgot password? Click here to reset